The (13)C chemical shifts of 19 methoxyflavonol derivatives have been modeled through using a structure-based quantitative structure-property relationship approach, which is based on the treatment of 2D images. In MIA-QSPR (multivariate image analysis applied to quantitative-structure-property relationships), descriptors correlating with dependent variables are pixels (binaries) of 2D chemical structures; variant pixels in the structures (substituents) account for the explained variance in the chemical shifts. Thus, a predictive model may be built from the regression between descriptors and experimental data. The MIA-QSPR approach coupled to partial least squares (PLS) regression built for the series of flavonols revealed that the predictive ability of MIA descriptors is comparable, or even superior for the fused rings moiety, when compared to the well-known Gauge Included Atomic Orbital (GIAO) procedure for (13)C chemical shifts calculations.