Endovascular repair is a minimal invasive alternative to open surgical therapy. From a long term perspective, complications such as prostheses displacement or leaks inside the aneurysm sac (endoleaks) could appear influencing the evolution of treatment. The objective of this work is to develop a preliminary Computer-aided diagnosis system (CAD) for an automated classification of EVAR progression from computed tomography angiography CTA images. The system is based on the extraction of texture features from thrombus aneurysm samples and a posterior classification. Regions of interest (ROIs) from patients with different post-EVAR evolution were extracted by experienced radiologists. Three conventional texture-analysis methods such as the gray level co-occurrence matrix (GLCM), the gray level run length matrix (GLRLM), and the gray level difference method (GLDM), were applied to each ROI to obtain texture features. Classification of the ROI is carried out by three different strategies. In the first one each feature set is fed to a neural network (NN). The second consists of a single neural network fed with a reduced version of texture features after a feature selection process. The third one comprised an ensembles of classifiers (ECs), formed by three NNs, each using as input one of the feature sets. The final decision is based on the application of a voting scheme across the outputs of the individual NNs. Classification results from the three classification strategies are evaluated using a receiver operating-characteristics (ROC) analysis and area under the roc curve (Az) performance. The multiple classification scheme using the three sets of texture features results in a better performance, as compared to the classification performance of the other alternatives.