This thesis proposes the engineering of a feature set that can qualify the tumours using textural and statistical measures, in order to predict the survival times of patients whom have been diagnosed with adenocarcinoma, a type of lung cancer. We consider the data in its 2D form, and create a benchmark using 2D Haralick computations and statistical shape measurements. Furthermore, we offer two additional schemes for feature set generation. Taking the benchmark, we analyze the feature measurements in relation to tumour depth. Cumulating this knowledge into a single measurementimproves the regression results, and also demonstrates the advantage of focusing on the prediction of short-term survival rate timelines. The second scheme considers the cancer nodule in its 3D entirety. This results in a large feature space, with over 100 dimensions. To process these, we explore dimensionality reduction techniques, particularly data diagonalization in a block-diagonal matrix manner, to further enhance regression results.