Gastric cancer, also known as stomach cancer, presents a significant health challenge, especially in East Asia, where it ranks among the leading causes of cancer-related death in countries like Japan, South Korea, and China. Early detection and precise characterization of gastric cancer are paramount for improving patient outcomes. In this study, we aim to harness the power of radiomic feature extraction through the Pyradiomics library to enhance the characterization of gastric cancer using medical imaging data collected from several Korean hospitals. Our research focuses on extracting key radiomic features, including Gray Level Co-occurrence Matrix (GLCM) features such as contrast, homogeneity, correlation, dissimilarity, and energy, as well as First Order Features like a energy, entropy, Mad, Root mean square and contrast. These extracted features served as the foundation for the classification process, wherein we employed advanced machine learning techniques. Leveraging radiomic features and advanced machine learning enhances interpretability and generalizability in gastric cancer characterization, complementing CNNs with comprehensive insights from smaller datasets and facilitating clinical data integration for improved predictive accuracy and computational efficiency in healthcare setting.