<p>Lung diseases are leading causes of morbidity and mortality globally, posing significant challenges for accurate diagnosis. Accurately diagnosing these conditions requires the expertise of experienced radiologists and doctors, making the process time-consuming. With the rapid growth of medical imaging data over recent decades, early and precise detection of lung disease has become increasingly vital for improving patient outcomes. Lung diseases are typically identified using X-ray and computed tomography (CT) scans, with both imaging techniques playing crucial roles in disease classification and retrieval based on the severity of the condition. To address these challenges, Content-Based Medical Image Retrieval (CBMIR) systems have emerged as essential tools, enabling the efficient indexing and retrieval of medical images, facilitating early detection, assessing disease severity, and monitoring therapeutic responses. This paper reviews CBMIR systems and detection techniques for lung diseases using CT and X-ray imaging, analyzing over 129 studies to identify the most effective methods across various contexts. The review also explores current limitations and outlines future directions in this rapidly evolving field. Our findings underscore the significant impact of machine learning, deep learning models, and advanced techniques in enhancing the accuracy and efficiency of lung disease detection and retrieval, highlighting the indispensable role of technology in modern healthcare.</p>