Images have always been seen as an effective medium for visual data presentation. In recent years, a tremendous combination of images and videos have been grown up rapidly due to technology evolution. Content-Based Visual Information Retrieval (CBVIR), which is the process of searching for images via the end user's predefined specific pattern (hand sketch, camera capture, or web scrawled). CBVIR is still far away from achieving objective satisfaction due to image content-based search engines (for ex. Google image-based search) still not completely satisfying. This problem occurs because of the semantic gap between low and high visual level features representation of the image. In this paper, The state-of-art CBVIR techniques for multi-purpose applications are survived. The architecture of the promising CBVIR pipelines in recent decades, which witness the arising of computer vision is highlighted. Mathematical, machine, and deep learning-based CBVIR systems are introduced. Although the high computational cost of deep learning techniques remains the most efficient to utilize.