The aim of the study is to investigate the ability of radiomics features to stratify patients based on CD8+ lymphocyte infiltration levels and identify relevant radiomics features associated with these levels. The data used in this study originates from two open-source repositories, TCIA and TCGA. The AI model was trained using TCIA data and tested on TCGA data. The results suggest that four texture features can confidently discriminate CD8+ infiltration levels (high/low). The model achieved a mean area under the curve AUC-ROC of 0.73(±0.08 std) on the training set and an AUC-ROC of 0.67 (95% CI: 53%, 80%) on the test set.