Advances in medical diagnostics necessitate innovative approaches to address the complexity of modern healthcare. This study introduces an automated diagnostic information system designed to enhance the accuracy and efficiency of gastroenterological disease diagnosis. Leveraging cosine similarity, the system analyzes high-dimensional signal data to identify relevant patient cases, achieving a diagnostic accuracy of 92% outperforming traditional metrics like Euclidean and Manhattan distances. The system processes diagnostic queries in real-time with an average runtime of 1.2 s, highlighting its clinical utility. By addressing limitations in existing systems, such as the lack of comparative diagnostics and automation, the proposed solution reduces physician workload and streamline decision-making. Its modular architecture ensures adaptability to new data, paving the way for continuous improvements. This research demonstrates the potential of cosine similarity in healthcare diagnostics, offering a scalable and efficient solution to improve patient outcomes and revolutionize medical decision-making.