This paper presents a comprehensive survey of deep learning techniques applied to the detection of lung diseases in medical images. While several studies have been conducted on this topic, there is a lack of surveys that provide taxonomy and analyze recent trends in the field. The objectives of this paper are to establish taxonomy of state-of-the-art deep learning-based Lung disease systems, visualize recent research trends, and identify remaining challenges and potential future directions. A total of ninety-eight articles published from 2016 to 2022 were reviewed and analyzed. The taxonomy comprises seven common attributes found in the surveyed articles, including image types, features, data augmentation, types of deep learning algorithms, transfer learning, ensemble of classifiers, and types of lung diseases. This taxonomy can serve as a valuable resource for researchers to plan their contributions and guide future research activities. Moreover, the identified potential future directions can lead to further improvements in the efficiency and expand the range of deep learning-aided Lung detection applications.